Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add adamjali/claude-skills --skill site-forgegit clone --depth 1 https://github.com/adamjali/claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adamjali/claude-skills/site-forge)<a href="https://agentmods.dev/skills/adamjali/claude-skills/site-forge"><img src="https://agentmods.dev/badge/skills/adamjali/claude-skills/site-forge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adamjali/claude-skills/site-forge"><img src="https://agentmods.dev/badge/skills/adamjali/claude-skills/site-forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00142 | $0.04931 |
| Opus 5 | $0.00071 | $0.02465 |
| Sonnet 5 | $0.00028 | $0.00986 |
| Haiku 4.5 | $0.00014 | $0.00493 |
Grade B, and why
site-forge scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
(`ls ~/.claude/skills` + plugin list). How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Forge
<execution_context> Phase 0 resolves the mode:
- auto (fast): Do as much as possible yourself. After the one plan/approval gate (Phase 3), run to completion without asking. Use only media you can make yourself for free (jina; MCP/Higgsfield if present). If a step blocks, needs interaction, or fails — skip it, keep going, list it under "Skipped / upgrade later" at the end. Bias to shipping.
- full (best quality): Interactive. Ask whenever a choice meaningfully changes the result, and use the best free media even when it needs the user (Google/Gemini for images, Veo 3.1 Fast in Flow for video — hand them exact prompts, they generate, drop the files). A blocked step → ask them to step in.
Both modes:
- 🟢 Auto: explore the environment, design, write code, extract frames, run ffmpeg, local-preview, and deploy after approval.
- 🟡 TWO mandatory gates in both modes: (1) the Phase 3 plan before building, and (2) the deploy itself — ask immediately before every deploy, every time. Approval for one deploy is never approval for the next. Default is local preview.
- 🔴 Never: invent fake credentials/keys; publish claims the user flagged as unverified without a disclaimer; enter the user's secrets into forms. </execution_context>
What ships with it
46 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 502 B
- assets/templates/index-skeleton.html 5.1 KB
- assets/templates/terrain/assets/favicon.svg 433 B
- assets/templates/terrain/assets/README.txt 437 B
- assets/templates/terrain/build.py 32 KB runs code
- assets/templates/terrain/DESIGN-SOURCE.md 1.7 KB
- assets/templates/terrain/index.html 41 KB
- assets/templates/terrain/README.md 4.7 KB
- assets/templates/terrain/skin.py 8.2 KB runs code
- evals/trigger-evals.json 2.5 KB
- references/aesthetics.md 3.9 KB
- references/ai-media.md 8.1 KB
- references/cms-options.md 5.5 KB
- references/components.md 52 KB
- references/deploy.md 16 KB
- references/design-profiles.md 7.4 KB
- references/design-stack.md 14 KB
- references/frontend-design.md 8.4 KB
- references/images.md 6.4 KB
- references/interactive-3d.md 24 KB
- references/page-composition.md 25 KB
- references/profile-creative-portfolio.md 13 KB
- references/profile-personal-agency.md 2.6 KB
- references/quality-checklist.md 65 KB
- references/reference-sites.md 12 KB
- references/remotion-video.md 12 KB
- references/scroll-effects.md 12 KB
- references/scroll-performance.md 12 KB
- references/seo-security-audit.md 5.3 KB
- references/stack-and-wiring.md 7.3 KB
- references/svg-line-work.md 9.9 KB
- references/twilio-a2p-10dlc.md 6.6 KB
- scripts/audit-seo.py 7.6 KB runs code
- scripts/build-captions.py 1.9 KB runs code
- scripts/check-crops.py 3.6 KB runs code
- scripts/check-shaders.js 2.8 KB runs code
- scripts/colour-system.py 5.9 KB runs code
- scripts/deploy-netlify.sh 2.5 KB runs code
- scripts/extract-frames.sh 867 B runs code
- scripts/hero-scrim.py 3.0 KB runs code
- scripts/make-dist.py 2.7 KB runs code
- scripts/mix-audio.sh 572 B runs code
- scripts/pick-hero.py 4.1 KB runs code
- scripts/render-video.sh 2.2 KB runs code
- scripts/verify-og.py 6.7 KB runs code
- scripts/verify-published.sh 1.0 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 313 lines · 142 tokens per session scan B 13b793291090
site-forge is a skill published in the GitHub repository adamjali/claude-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 4,931 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
colors
Color systems for web interfaces — OKLCH conversion and palette generation, contrast measurement (APCA/WCAG), gamut and P3 fallbacks, theming, one meaning per color. INVOKE PROACTIVELY when converting color values, building or extending a palette or token set, checking or reporting contrast, or theming light and dark…
branch-recap
Takes stock of what a branch actually changed, before it gets pushed — works out the scope itself, then lays the change out group by group in one pass: files touched, what was done and why, how, and what deserves a second look, quoting code only where a remark needs it rather than reprinting the diffs. Closes on a…
audit-context
Measures where a project's Claude context is going before applying any of clean-context's levers. Reports what Glob discovers with and without ignore files applied, the twenty largest files in the repo and which are generated, the cumulative size of every CLAUDE.md loaded for this working directory, and how many MCP…
accessibility
Accessibility engineering for product interfaces — keyboard support, focus states, ARIA, forms, screen readers, hit areas, motion and zoom. INVOKE PROACTIVELY when building or reviewing any UI component, modal, menu, form, or custom widget, and on any keyboard or screen-reader complaint — even when nobody says "a11y".…
ui-polish
Design-engineering details that make an interface feel polished — border radius, optical alignment, shadows and elevation, animations and micro-interactions, press feedback, icons. INVOKE PROACTIVELY when building or reviewing UI components, adding motion or hover/active states, or when the user says "make it feel…
layout
Layout structure for web interfaces — grouping, alignment, negative space, reading order, progressive disclosure, breakpoints, direction-aware (RTL) structure. INVOKE PROACTIVELY when structuring a page or component, spacing or aligning controls, deciding what collapses at small sizes, or reviewing frontend structure.…